[Qemu-devel] [PATCH v2 11/13] target-arm: A64: Add narrowing 2-reg-misc instructions

[Peter Maydell <peter.maydell@linaro.org>]

Add the narrowing integer instructions in the 2-reg-misc class.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 85 ++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 83 insertions(+), 2 deletions(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index dd1bbeb..42457e4 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -75,6 +75,8 @@ typedef struct AArch64DecodeTable {
 /* Function prototype for gen_ functions for calling Neon helpers */
 typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32);
 typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
+typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64);
+typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64);
 
 /* initialize TCG globals.  */
 void a64_translate_init(void)
@@ -7371,6 +7373,79 @@ static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn)
     }
 }
 
+static void handle_2misc_narrow(DisasContext *s, int opcode, bool u, bool is_q,
+                                int size, int rn, int rd)
+{
+    /* Handle 2-reg-misc ops which are narrowing (so each 2*size element
+     * in the source becomes a size element in the destination).
+     */
+    int pass;
+    TCGv_i32 tcg_res[2];
+    int destelt = is_q ? 2 : 0;
+
+    for (pass = 0; pass < 2; pass++) {
+        TCGv_i64 tcg_op = tcg_temp_new_i64();
+        NeonGenNarrowFn *genfn = NULL;
+        NeonGenNarrowEnvFn *genenvfn = NULL;
+
+        read_vec_element(s, tcg_op, rn, pass, MO_64);
+        tcg_res[pass] = tcg_temp_new_i32();
+
+        switch (opcode) {
+        case 0x12: /* XTN, SQXTUN */
+        {
+            static NeonGenNarrowFn * const xtnfns[3] = {
+                gen_helper_neon_narrow_u8,
+                gen_helper_neon_narrow_u16,
+                tcg_gen_trunc_i64_i32,
+            };
+            static NeonGenNarrowEnvFn * const sqxtunfns[3] = {
+                gen_helper_neon_unarrow_sat8,
+                gen_helper_neon_unarrow_sat16,
+                gen_helper_neon_unarrow_sat32,
+            };
+            if (u) {
+                genenvfn = sqxtunfns[size];
+            } else {
+                genfn = xtnfns[size];
+            }
+            break;
+        }
+        case 0x14: /* SQXTN, UQXTN */
+        {
+            static NeonGenNarrowEnvFn * const fns[3][2] = {
+                { gen_helper_neon_narrow_sat_s8,
+                  gen_helper_neon_narrow_sat_u8 },
+                { gen_helper_neon_narrow_sat_s16,
+                  gen_helper_neon_narrow_sat_u16 },
+                { gen_helper_neon_narrow_sat_s32,
+                  gen_helper_neon_narrow_sat_u32 },
+            };
+            genenvfn = fns[size][u];
+            break;
+        }
+        default:
+            g_assert_not_reached();
+        }
+
+        if (genfn) {
+            genfn(tcg_res[pass], tcg_op);
+        } else {
+            genenvfn(tcg_res[pass], cpu_env, tcg_op);
+        }
+
+        tcg_temp_free_i64(tcg_op);
+    }
+
+    for (pass = 0; pass < 2; pass++) {
+        write_vec_element_i32(s, tcg_res[pass], rd, destelt + pass, MO_32);
+        tcg_temp_free_i32(tcg_res[pass]);
+    }
+    if (!is_q) {
+        clear_vec_high(s, rd);
+    }
+}
+
 /* C3.6.17 AdvSIMD two reg misc
  *   31  30  29 28       24 23  22 21       17 16    12 11 10 9    5 4    0
  * +---+---+---+-----------+------+-----------+--------+-----+------+------+
@@ -7405,11 +7480,17 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
         }
         unallocated_encoding(s);
         return;
+    case 0x12: /* XTN, XTN2, SQXTUN, SQXTUN2 */
+    case 0x14: /* SQXTN, SQXTN2, UQXTN, UQXTN2 */
+        if (size == 3) {
+            unallocated_encoding(s);
+            return;
+        }
+        handle_2misc_narrow(s, opcode, u, is_q, size, rn, rd);
+        return;
     case 0x2: /* SADDLP, UADDLP */
     case 0x4: /* CLS, CLZ */
     case 0x6: /* SADALP, UADALP */
-    case 0x12: /* XTN, XTN2, SQXTUN, SQXTUN2 */
-    case 0x14: /* SQXTN, SQXTN2, UQXTN, UQXTN2 */
         if (size == 3) {
             unallocated_encoding(s);
             return;
-- 
1.8.5